基于子图选择的土种识别——以重庆市璧山区紫色土为例  

Soil Species Classification Based on Subgraph Selection:Take the Purple Soil in Bishan District,Chongqing City as an Example

作　　者：陈怡达 曾绍华[1,2] 吴雪 王帅 刘国一 周鹏 CHEN Yida;ZENG Shaohua;WU Xue;WANG Shuai;LIU Guoyi;ZHOU Peng(College of Computer and Information Science,Chongqing Normal University;Chongqing Center of Engineering Technology Research on Digital Agricultural Service,Chongqing40133l;The Center of Agricultural Technology Promotion of Nanchuan District,Nanchuan Chongqing 408400;Chongqing Master Station of Agricultural Technology Promotion,Chongqing 400121;Institute of Agricultural Resources and Environment,Tibet Academy of Agricultural and Animal Husbandry Sciences,Lhasa 850032;The Center of Agricultural Technology Service of Fengjie County,Fengjie Chongqing 404600,China)

机构地区：[1]重庆师范大学计算机与信息科学学院 [2]重庆师范大学重庆市数字农业服务工程技术研究中心,重庆401331 [3]重庆市南川区农业技术推广中心,重庆南川408400 [4]重庆市农业技术推广总站,重庆400121 [5]西藏自治区农牧科学院农业资源与环境研究所,拉萨850032 [6]重庆市奉节县农业技术服务中心,重庆奉节404600

出　　处：《重庆师范大学学报（自然科学版）》2024年第3期59-72,共14页Journal of Chongqing Normal University:Natural Science

基　　金：重庆市教育委员会科学技术研究计划重点项目(No.KJZD-K201900505);重庆市高校创新研究群体(No.CXQT20015);重庆市技术预见与制度创新项目(No.CSTB2022TFII-OFX0043);重庆师范大学研究生科研创新项目(No.YKC22016)。

摘　　要：针对机器视觉野外自然条件下采集土壤图像包含阴影、空洞、缝隙等可能对土种识别产生影响的因素,和土壤图像采集、标记成本高,样本量小的问题,提出一种基于土壤子图选择的土种识别方法。该方法以局部阴影最小化及空间距离最大化为准则,构造最优化模型;并基于最大最小距离算法思想,迭代更新距离矩阵求解优化模型,获得选择子图中心点,构建土壤子图数据集。实验结果显示:土壤子图选择算法构建的数据集在3个不同深度ResNet模型下训练、识别测试,均有较好的训练、识别精度;在土壤子图选择α参数为1、子图尺寸为224时,在浅层网络ResNet-18下能达到最佳测试结果,训练的网络模型在验证集识别准确率为92.48%,测试集识别准确率为92.95%,相较于土壤原图数据集的最佳土种识别结果提升46.65%;利用最小外接矩阵能加速相较于不使用加速,子图选择算法提升运算速度38.88%。基于子图选择的土种识别大幅度提升了土种识别准确率,证明算法是有效的。The presence of shadows,holes,and gaps on soil images collected under natural conditions has a significant negative impact on machine vision classification of soil species.And the sample size for machine vision-based soil species identification is generally insufficient due to the high cost of acquiring and labeling soil photographs.A soil species classification method is presented based on subgraph selection to address above problems.The proposed approach first constructs an optimal model to select the centers of soil subgraph according to the principles of local shadow minimization and spatial distance maximization.And then creates a soil sub-image dataset on the basis of a center set obtained by iteratively updating a distance matrix utilizing above optimization model.Experimental results demonstrate that soil subgraph datasets established by the subgraph selection algorithm exhibit excellent performance on three ResNet models with different depths.ResNet-18 performs best when setting the adaptive factorαto 1 and the sub-image size is 224,with a validation set classification accuracy of 92.48%and a test set classification accuracy of 92.95%.In addition,it is 46.65%superior than the best classification result of the soil species classification model rained with the original soil image dataset.These prove that the accuracy of soil classification based on the subgraph selection algorithm is promoted andthealgorithm iseffective.

关 键 词：土种识别 子图选择 深度学习 土壤图像 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]